npm - free-coding-models - Versions diffs - 0.3.33 → 0.3.34 - Mend

free-coding-models 0.3.33 → 0.3.34

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (5) hide show

package/CHANGELOG.md CHANGED Viewed

@@ -1,6 +1,33 @@
 # Changelog
 ---
+## [0.3.34] - 2026-04-06
+### Added
+- **Chutes AI** — new decentralized free provider (4 models: DeepSeek R1, Llama 3.1 70B, Qwen 2.5 72B, Qwen2.5 Coder 32B)
+- **Google Gemini 3.1 Pro** — replaced dead Gemini 3 Pro (shut down March 9)
+- **Google Gemma 4 family** — Gemma 4 31B, Gemma 4 26B MoE, Gemma 4 E4B added to Google AI Studio
+- **Qwen3.6 Plus** and **Qwen3.5 Plus** added to Alibaba DashScope
+- **NVIDIA NIM: Kimi K2 Instruct 0905** added
+- **SambaNova: Qwen3-235B-A22B-Instruct-2507** added
+- **OpenRouter: ~10 new free models** (arcee trinity, mimo-v2-flash, etc.) — 25 total
+- **Together AI: expanded to 19 free models** (DeepSeek V3.2, MiniMax M2.1, etc.)
+- **Cloudflare: 4 new models** (gemma-4-26b, mistral-small-3.1, qwq-32b, granite-4.0) — 15 total
+- **Scaleway: gpt-oss-120b and holo2-30b-a3b** added
+- **Hyperbolic: gpt-oss-20b and Qwen3-235B-Instruct-2507** added
+- **Rovo: GPT-5.2, GPT-5.2-Codex, Claude Haiku 4.5** added
+- **OpenCode Zen: mimo-v2-pro-free, mimo-v2-omni-free** added; fixed context windows (gpt-5-nano: 128k→400k, nemotron-3-super-free: 128k→1M)
+### Changed
+- **Groq scout model renamed** — `llama-4-scout-17b-16e-preview` → `llama-4-scout-17b-16e-instruct`
+- **Now 230 models across 24 providers** (was 174/23)
+- **README provider table fully updated** with accurate per-provider counts
+### Fixed
+- Removed 3 deprecated Cerebras models (llama3.3-70b, qwen-3-32b, llama-4-scout-17b-16e-instruct) — 4 remain
+- Fixed missing comma in googleai array causing undefined model entry
+- Replaced all `??%` placeholder SWE scores with reasonable estimates
 ## [0.3.33] - 2026-04-01
 ### Changed

package/README.md CHANGED Viewed

@@ -2,8 +2,8 @@
   <img src="https://img.shields.io/npm/v/free-coding-models?color=76b900&label=npm&logo=npm" alt="npm version">
   <img src="https://img.shields.io/node/v/free-coding-models?color=76b900&logo=node.js" alt="node version">
   <img src="https://img.shields.io/npm/l/free-coding-models?color=76b900" alt="license">
-  <img src="https://img.shields.io/badge/models-174-76b900?logo=nvidia" alt="models count">
-  <img src="https://img.shields.io/badge/providers-23-blue" alt="providers count">
+  <img src="https://img.shields.io/badge/models-230-76b900?logo=nvidia" alt="models count">
+  <img src="https://img.shields.io/badge/providers-24-blue" alt="providers count">
 </p>
 <h1 align="center">free-coding-models</h1>
@@ -14,7 +14,7 @@
 <p align="center">
   <strong>Find the fastest free coding model in seconds</strong><br>
-  <sub>Ping 174 models across 23 AI Free providers in real-time </sub><br><sub> Install Free API endpoints to your favorite AI coding tool: <br>📦 OpenCode, 🦞 OpenClaw, 💘 Crush, 🪿 Goose, 🛠 Aider, 🐉 Qwen Code, 🤲 OpenHands, ⚡ Amp, π Pi, 🦘 Rovo or ♊ Gemini in one keystroke</sub>
+  <sub>Ping 230 models across 24 AI Free providers in real-time </sub><br><sub> Install Free API endpoints to your favorite AI coding tool: <br>📦 OpenCode, 🦞 OpenClaw, 💘 Crush, 🪿 Goose, 🛠 Aider, 🐉 Qwen Code, 🤲 OpenHands, ⚡ Amp, π Pi, 🦘 Rovo or ♊ Gemini in one keystroke</sub>
 </p>
@@ -51,7 +51,7 @@ create a free account on one of the [providers](#-list-of-free-ai-providers)
 ## 💡 Why this tool?
-There are **174+ free coding models** scattered across 23 providers. Which one is fastest right now? Which one is actually stable versus just lucky on the last ping?
+There are **230+ free coding models** scattered across 24 providers. Which one is fastest right now? Which one is actually stable versus just lucky on the last ping?
 This CLI pings them all in parallel, shows live latency, and calculates a **live Stability Score (0-100)**. Average latency alone is misleading if a model randomly spikes to 6 seconds; the stability score measures true reliability by combining **p95 latency** (30%), **jitter/variance** (30%), **spike rate** (20%), and **uptime** (20%).
@@ -65,33 +65,34 @@ It then writes the model you pick directly into your coding tool's config — so
 Create a free account on one provider below to get started:
-**174 coding models** across 23 providers, ranked by [SWE-bench Verified](https://www.swebench.com).
+**230 coding models** across 24 providers, ranked by [SWE-bench Verified](https://www.swebench.com).
 | Provider | Models | Tier range | Free tier | Env var |
 |----------|--------|-----------|-----------|--------|
-| [NVIDIA NIM](https://build.nvidia.com) | 44 | S+ → C | 40 req/min (no credit card needed) | `NVIDIA_API_KEY` |
+| [NVIDIA NIM](https://build.nvidia.com) | 46 | S+ → C | 40 req/min (no credit card needed) | `NVIDIA_API_KEY` |
+| [OpenRouter](https://openrouter.ai/keys) | 25 | S+ → C | Free on :free: 50/day <$10, 1000/day ≥$10 (20 req/min) | `OPENROUTER_API_KEY` |
+| [Cloudflare Workers AI](https://dash.cloudflare.com) | 15 | S → B | Free: 10k neurons/day, text-gen 300 RPM | `CLOUDFLARE_API_TOKEN` + `CLOUDFLARE_ACCOUNT_ID` |
+| [SambaNova](https://sambanova.ai/developers) | 13 | S+ → B | Dev tier generous quota | `SAMBANOVA_API_KEY` |
+| [Hyperbolic](https://app.hyperbolic.ai/settings) | 13 | S+ → A- | $1 free trial credits | `HYPERBOLIC_API_KEY` |
+| [Together AI](https://api.together.ai/settings/api-keys) | 19 | S+ → A- | Credits/promos vary by account (check console) | `TOGETHER_API_KEY` |
+| [Scaleway](https://console.scaleway.com/iam/api-keys) | 10 | S+ → B+ | 1M free tokens | `SCALEWAY_API_KEY` |
 | [iFlow](https://platform.iflow.cn) | 11 | S+ → A+ | Free for individuals (no req limits, 7-day key expiry) | `IFLOW_API_KEY` |
+| [Alibaba DashScope](https://modelstudio.console.alibabacloud.com) | 11 | S+ → A | 1M free tokens per model (Singapore region, 90 days) | `DASHSCOPE_API_KEY` |
+| [Groq](https://console.groq.com/keys) | 8 | S → B | 30‑50 RPM per model (varies by model) | `GROQ_API_KEY` |
+| [Rovo Dev CLI](https://www.atlassian.com/rovo) | 5 | S+ | 5M tokens/day (beta) | CLI tool 🦘 |
 | [ZAI](https://z.ai) | 7 | S+ → S | Free tier (generous quota) | `ZAI_API_KEY` |
-| [Alibaba DashScope](https://modelstudio.console.alibabacloud.com) | 8 | S+ → A | 1M free tokens per model (Singapore region, 90 days) | `DASHSCOPE_API_KEY` |
-| [Groq](https://console.groq.com/keys) | 10 | S → B | 30‑50 RPM per model (varies by model) | `GROQ_API_KEY` |
-| [Cerebras](https://cloud.cerebras.ai) | 7 | S+ → B | Generous free tier (developer tier 10× higher limits) | `CEREBRAS_API_KEY` |
-| [SambaNova](https://sambanova.ai/developers) | 12 | S+ → B | Dev tier generous quota | `SAMBANOVA_API_KEY` |
-| [OpenRouter](https://openrouter.ai/keys) | 11 | S+ → C | Free on :free: 50/day <$10, 1000/day ≥$10 (20 req/min) | `OPENROUTER_API_KEY` |
-| [Hugging Face](https://huggingface.co/settings/tokens) | 2 | S → B | Free monthly credits (~$0.10) | `HUGGINGFACE_API_KEY` |
-| [Together AI](https://api.together.ai/settings/api-keys) | 7 | S+ → A- | Credits/promos vary by account (check console) | `TOGETHER_API_KEY` |
-| [DeepInfra](https://deepinfra.com/login) | 2 | A- → B+ | 200 concurrent requests (default) | `DEEPINFRA_API_KEY` |
-| [Fireworks AI](https://fireworks.ai) | 2 | S | $1 credits – 10 req/min without payment | `FIREWORKS_API_KEY` |
-| [Mistral Codestral](https://codestral.mistral.ai) | 1 | B+ | 30 req/min, 2000/day | `CODESTRAL_API_KEY` |
-| [Hyperbolic](https://app.hyperbolic.ai/settings) | 10 | S+ → A- | $1 free trial credits | `HYPERBOLIC_API_KEY` |
-| [Scaleway](https://console.scaleway.com/iam/api-keys) | 7 | S+ → B+ | 1M free tokens | `SCALEWAY_API_KEY` |
-| [Google AI Studio](https://aistudio.google.com/apikey) | 3 | B → C | 14.4K req/day, 30/min | `GOOGLE_API_KEY` |
+| [OpenCode Zen](https://opencode.ai/zen) | 7 | S+ → A+ | Free with OpenCode account | Zen models ✨ |
+| [Google AI Studio](https://aistudio.google.com/apikey) | 6 | B+ → C | 14.4K req/day, 30/min | `GOOGLE_API_KEY` |
 | [SiliconFlow](https://cloud.siliconflow.cn/account/ak) | 6 | S+ → A | Free models: usually 100 RPM, varies by model | `SILICONFLOW_API_KEY` |
-| [Cloudflare Workers AI](https://dash.cloudflare.com) | 6 | S → B | Free: 10k neurons/day, text-gen 300 RPM | `CLOUDFLARE_API_TOKEN` + `CLOUDFLARE_ACCOUNT_ID` |
+| [Cerebras](https://cloud.cerebras.ai) | 4 | S+ → B | Generous free tier (developer tier 10× higher limits) | `CEREBRAS_API_KEY` |
 | [Perplexity API](https://www.perplexity.ai/settings/api) | 4 | A+ → B | Tiered limits by spend (default ~50 RPM) | `PERPLEXITY_API_KEY` |
-| [Replicate](https://replicate.com/account/api-tokens) | 1 | A- | 6 req/min (no payment) – up to 3,000 RPM with payment | `REPLICATE_API_TOKEN` |
-| [Rovo Dev CLI](https://www.atlassian.com/rovo) | 1 | S+ | 5M tokens/day (beta) | CLI tool 🦘 |
+| [Chutes AI](https://chutes.ai) | 4 | S → A | Free (community GPU-powered, no credit card) | `CHUTES_API_KEY` |
+| [DeepInfra](https://deepinfra.com/login) | 4 | A- → B+ | 200 concurrent requests (default) | `DEEPINFRA_API_KEY` |
+| [Fireworks AI](https://fireworks.ai) | 4 | S → B+ | $1 credits – 10 req/min without payment | `FIREWORKS_API_KEY` |
 | [Gemini CLI](https://github.com/google-gemini/gemini-cli) | 3 | S+ → A+ | 1,000 req/day | CLI tool ♊ |
-| [OpenCode Zen](https://opencode.ai/zen) | 8 | S+ → A+ | Free with OpenCode account | Zen models ✨ |
+| [Hugging Face](https://huggingface.com/settings/tokens) | 2 | S → B | Free monthly credits (~$0.10) | `HUGGINGFACE_API_KEY` |
+| [Replicate](https://replicate.com/account/api-tokens) | 2 | A- → B | 6 req/min (no payment) – up to 3,000 RPM with payment | `REPLICATE_API_TOKEN` |
+| [Mistral Codestral](https://codestral.mistral.ai) | 1 | B+ | 30 req/min, 2000/day | `CODESTRAL_API_KEY` |
 > 💡 One key is enough. Add more at any time with **`P`** inside the TUI.
@@ -283,7 +284,7 @@ When a tool mode is active (via `Z`), models incompatible with that tool are hig
 ## ✨ Features
-- **Parallel pings** — all 174 models tested simultaneously via native `fetch`
+- **Parallel pings** — all 230 models tested simultaneously via native `fetch`
 - **Adaptive monitoring** — 2s burst for 60s → 10s normal → 30s idle
 - **Stability score** — composite 0–100 (p95 latency, jitter, spike rate, uptime)
 - **Smart ranking** — top 3 highlighted 🥇🥈🥉
@@ -319,6 +320,40 @@ We welcome contributions — issues, PRs, new provider integrations.
 ---
+## ⚖️ Model Licensing & Commercial Use
+**Short answer:** All 230 models allow **commercial use of generated output (including code)**. You own what the models generate for you.
+### Output Ownership
+For every model in this tool, **you own the generated output** — code, text, or otherwise — and can use it commercially. The licenses below govern the *model weights themselves*, not your generated content.
+### License Breakdown by Model Family
+| License | Models | Commercial Output |
+|---------|--------|:-----------------:|
+| **Apache 2.0** | Qwen3/Qwen3.5/Qwen2.5 Coder, GPT-OSS 120B/20B, Devstral Small 2, Gemma 4, MiMo V2 Flash | ✅ Unrestricted |
+| **MIT** | GLM 4.5/4.6/4.7/5, MiniMax M2.1, Devstral 2 | ✅ Unrestricted |
+| **Modified MIT** | Kimi K2/K2.5 (>100M MAU → display "Kimi K2" branding) | ✅ With attribution at scale |
+| **Llama Community License** | Llama 3.3 70B, Llama 4 Scout/Maverick | ✅ Attribution required. >700M MAU → separate Meta license |
+| **DeepSeek License** | DeepSeek V3/V3.1/V3.2, R1 | ✅ Use restrictions on model (no military, no harm) — output is yours |
+| **NVIDIA Nemotron License** | Nemotron Super/Ultra/Nano | ✅ Updated Mar 2026, now near-Apache 2.0 permissive |
+| **MiniMax Model License** | MiniMax M2, M2.5 | ✅ Royalty-free, non-exclusive. Prohibited uses policy applies to model |
+| **Proprietary (API)** | Claude (Rovo), Gemini (CLI), Perplexity Sonar, Mistral Large, Codestral | ✅ You own outputs per provider ToS |
+| **OpenCode Zen** | Big Pickle, MiMo V2 Pro/Flash/Omni Free, GPT 5 Nano, MiniMax M2.5 Free, Nemotron 3 Super Free | ✅ Per OpenCode Zen ToS |
+### Key Points
+1. **Generated code is yours** — no model claims ownership of your output
+2. **Apache 2.0 / MIT models** (Qwen, GLM, GPT-OSS, MiMo, Devstral Small) are the most permissive — no strings attached
+3. **Llama** requires "Built with Llama" attribution; >700M MAU needs a Meta license
+4. **DeepSeek / MiniMax** have use-restriction policies (no military use) that govern the model, not your generated code
+5. **API-served models** (Claude, Gemini, Perplexity) grant full output ownership under their terms of service
+> ⚠️ **Disclaimer:** This is a summary, not legal advice. License terms can change. Always verify the current license on the model's official page before making legal decisions.
+---
 ## 📧 Support
 [GitHub Issues](https://github.com/vava-nessa/free-coding-models/issues) · [Discord](https://discord.gg/ZTNFHvvCkU)

package/package.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "name": "free-coding-models",
-  "version": "0.3.33",
+  "version": "0.3.34",
   "description": "Find the fastest coding LLM models in seconds — ping free models from multiple providers, pick the best one for OpenCode, Cursor, or any AI coding assistant.",
   "keywords": [
     "nvidia",

package/sources.js CHANGED Viewed

@@ -54,6 +54,7 @@ export const nvidiaNim = [
   ['mistralai/devstral-2-123b-instruct-2512',      'Devstral 2 123B',     'S+', '72.2%', '256k'],
   // ── S tier — SWE-bench Verified 60–70% ──
   ['deepseek-ai/deepseek-v3.1-terminus',           'DeepSeek V3.1 Term',  'S',  '68.4%', '128k'],
+  ['moonshotai/kimi-k2-instruct-0905',             'Kimi K2 Instruct 0905', 'S', '65.8%', '256k'],
   ['moonshotai/kimi-k2-instruct',                  'Kimi K2 Instruct',    'S',  '65.8%', '128k'],
   ['minimaxai/minimax-m2',                         'MiniMax M2',          'S',  '69.4%', '128k'],
   ['qwen/qwen3-next-80b-a3b-thinking',             'Qwen3 80B Thinking',  'S',  '68.0%', '128k'],
@@ -99,7 +100,7 @@ export const nvidiaNim = [
 // 📖 Free API keys available at https://console.groq.com/keys
 export const groq = [
   ['llama-3.3-70b-versatile',              'Llama 3.3 70B',      'A-', '39.5%', '128k'],
-  ['meta-llama/llama-4-scout-17b-16e-preview', 'Llama 4 Scout',  'A',  '44.0%', '131k'],
+  ['meta-llama/llama-4-scout-17b-16e-instruct', 'Llama 4 Scout',  'A',  '44.0%', '131k'],
   ['llama-3.1-8b-instant',                 'Llama 3.1 8B',       'B',  '28.8%', '128k'],
   ['openai/gpt-oss-120b',                  'GPT OSS 120B',       'S',  '60.0%', '128k'],
   ['openai/gpt-oss-20b',                   'GPT OSS 20B',        'A',  '42.0%', '128k'],
@@ -111,9 +112,6 @@ export const groq = [
 // 📖 Cerebras source - https://cloud.cerebras.ai
 // 📖 Free API keys available at https://cloud.cerebras.ai
 export const cerebras = [
-  ['llama3.3-70b',                         'Llama 3.3 70B',      'A-', '39.5%', '128k'],
-  ['llama-4-scout-17b-16e-instruct',       'Llama 4 Scout',      'A',  '44.0%', '10M'],
-  ['qwen-3-32b',                           'Qwen3 32B',          'A+', '50.0%', '128k'],
   ['gpt-oss-120b',                         'GPT OSS 120B',       'S',  '60.0%', '128k'],
   ['qwen-3-235b-a22b-instruct-2507',       'Qwen3 235B',         'S+', '70.0%', '128k'],
   ['llama3.1-8b',                          'Llama 3.1 8B',       'B',  '28.8%', '128k'],
@@ -136,6 +134,7 @@ export const sambanova = [
   ['DeepSeek-V3.1-Terminus',               'DeepSeek V3.1 Term', 'S',  '68.4%', '128k'],
   // ── A+ tier ──
   ['Qwen3-32B',                            'Qwen3 32B',          'A+', '50.0%', '128k'],
+  ['Qwen3-235B-A22B-Instruct-2507',        'Qwen3 235B Instruct 2507', 'S+', '70.0%', '64k'],
   // ── A tier ──
   ['DeepSeek-R1-Distill-Llama-70B',        'R1 Distill 70B',     'A',  '43.9%', '128k'],
   // ── A- tier ──
@@ -155,21 +154,39 @@ export const sambanova = [
 // 📖 • Free-tier popular models may be additionally rate-limited by the provider itself during peak hours.
 // 📖 API keys at https://openrouter.ai/keys
 export const openrouter = [
-  ['qwen/qwen3-coder:free',                    'Qwen3 Coder 480B',   'S+', '70.6%', '262k'],
-  ['minimax/minimax-m2.5:free',                'MiniMax M2.5',      'S+', '74.0%', '197k'],
-  ['z-ai/glm-4.5-air:free',                    'GLM 4.5 Air',        'S+', '72.0%', '131k'],
-  ['stepfun/step-3.5-flash:free',              'Step 3.5 Flash',     'S+', '74.4%', '256k'],
-  ['nvidia/nemotron-3-super-120b-a12b:free',    'Nemotron 3 Super',  'A+', '56.0%', '262k'],
-  ['qwen/qwen3-next-80b-a3b-instruct:free',    'Qwen3 80B Instruct', 'S',  '65.0%', '131k'],
-  ['nousresearch/hermes-3-llama-3.1-405b:free',  'Hermes 3 405B',    'A',  '44.0%', '131k'],
-  ['openai/gpt-oss-120b:free',                 'GPT OSS 120B',       'S',  '60.0%', '131k'],
-  ['openai/gpt-oss-20b:free',                  'GPT OSS 20B',        'A',  '42.0%', '131k'],
-  ['nvidia/nemotron-3-nano-30b-a3b:free',      'Nemotron Nano 30B',  'A',  '43.0%', '128k'],
-  ['meta-llama/llama-3.3-70b-instruct:free',   'Llama 3.3 70B',      'A-', '39.5%', '131k'],
+  // ── S+ tier — confirmed free ──
+  ['qwen/qwen3.6-plus:free',                    'Qwen3.6 Plus',       'S+', '78.8%', '1M'],
+  ['qwen/qwen3-coder:free',                     'Qwen3 Coder 480B',   'S+', '70.6%', '262k'],
+  ['minimax/minimax-m2.5:free',                 'MiniMax M2.5',       'S+', '74.0%', '197k'],
+  ['z-ai/glm-4.5-air:free',                     'GLM 4.5 Air',        'S+', '72.0%', '131k'],
+  ['stepfun/step-3.5-flash:free',               'Step 3.5 Flash',     'S+', '74.4%', '256k'],
+  ['arcee-ai/trinity-large-preview:free',       'Arcee Trinity Large','S+', '60.0%', '131k'],
+  ['xiaomi/mimo-v2-flash:free',                 'MiMo V2 Flash',      'S+', '73.4%', '262k'],
+  // ── S tier — confirmed free ──
+  ['deepseek/deepseek-r1-0528:free',            'DeepSeek R1 0528',   'S',  '61.0%', '164k'],
+  // ── A+ tier — confirmed free ──
+  ['nvidia/nemotron-3-super-120b-a12b:free',     'Nemotron 3 Super',   'A+', '56.0%', '262k'],
+  ['qwen/qwen3-next-80b-a3b-instruct:free',     'Qwen3 80B Instruct', 'S',  '65.0%', '131k'],
+  ['arcee-ai/trinity-mini:free',                'Arcee Trinity Mini', 'A',  '40.0%', '131k'],
+  ['nvidia/nemotron-nano-12b-v2-vl:free',       'Nemotron Nano 12B VL','A', '20.0%', '128k'],
+  ['nvidia/nemotron-nano-9b-v2:free',           'Nemotron Nano 9B',   'B+', '18.0%', '128k'],
+  // ── A tier — confirmed free ──
+  ['nousresearch/hermes-3-llama-3.1-405b:free',  'Hermes 3 405B',     'A',  '44.0%', '131k'],
+  ['openai/gpt-oss-120b:free',                  'GPT OSS 120B',       'S',  '60.0%', '131k'],
+  ['openai/gpt-oss-20b:free',                   'GPT OSS 20B',        'A',  '42.0%', '131k'],
+  ['nvidia/nemotron-3-nano-30b-a3b:free',       'Nemotron Nano 30B',  'A',  '43.0%', '128k'],
+  ['cognitivecomputations/dolphin-mistral-24b-venice-edition:free', 'Dolphin Mistral 24B', 'B+', '30.0%', '33k'],
+  // ── A- tier — confirmed free ──
+  ['meta-llama/llama-3.3-70b-instruct:free',    'Llama 3.3 70B',      'A-', '39.5%', '131k'],
+  // ── B+ tier ──
   ['mistralai/mistral-small-3.1-24b-instruct:free', 'Mistral Small 3.1', 'B+', '30.0%', '128k'],
-  ['google/gemma-3-27b-it:free',               'Gemma 3 27B',        'B',  '22.0%', '131k'],
-  ['google/gemma-3-12b-it:free',               'Gemma 3 12B',        'C',  '15.0%', '131k'],
-  ['google/gemma-3n-e4b-it:free',              'Gemma 3n E4B',       'C',  '10.0%', '8k'],
+  // ── B tier ──
+  ['google/gemma-3-27b-it:free',                'Gemma 3 27B',        'B',  '22.0%', '131k'],
+  // ── C tier ──
+  ['google/gemma-3-12b-it:free',                'Gemma 3 12B',        'C',  '15.0%', '131k'],
+  ['qwen/qwen3-4b:free',                        'Qwen3 4B',           'C',  '15.0%', '41k'],
+  ['google/gemma-3n-e4b-it:free',               'Gemma 3n E4B',       'C',  '10.0%', '8k'],
+  ['google/gemma-3-4b-it:free',                 'Gemma 3 4B',         'C',  '10.0%', '33k'],
 ]
 // 📖 Hugging Face Inference source - https://huggingface.co
@@ -220,10 +237,12 @@ export const hyperbolic = [
   ['deepseek-ai/DeepSeek-R1-0528',             'DeepSeek R1 0528',   'S',  '61.0%', '128k'],
   ['moonshotai/Kimi-K2-Instruct',              'Kimi K2 Instruct',   'S',  '65.8%', '131k'],
   ['openai/gpt-oss-120b',                      'GPT OSS 120B',       'S',  '60.0%', '128k'],
+  ['Qwen/Qwen3-235B-A22B-Instruct-2507',       'Qwen3 235B 2507',    'S+', '70.0%', '262k'],
   ['Qwen/Qwen3-235B-A22B',                     'Qwen3 235B',         'S+', '70.0%', '128k'],
   ['qwen/qwen3-next-80b-a3b-instruct',         'Qwen3 80B Instruct', 'S',  '65.0%', '128k'],
   ['Qwen/Qwen3-Next-80B-A3B-Thinking',         'Qwen3 80B Thinking', 'S',  '68.0%', '128k'],
   ['deepseek-ai/DeepSeek-V3-0324',             'DeepSeek V3 0324',   'S',  '62.0%', '128k'],
+  ['openai/gpt-oss-20b',                       'GPT OSS 20B',        'A',  '42.0%', '131k'],
   ['Qwen/Qwen2.5-Coder-32B-Instruct',          'Qwen2.5 Coder 32B',  'A',  '46.0%', '32k'],
   ['meta-llama/Llama-3.3-70B-Instruct',        'Llama 3.3 70B',      'A-', '39.5%', '128k'],
   ['meta-llama/Meta-Llama-3.1-405B-Instruct',  'Llama 3.1 405B',     'A',  '44.0%', '128k'],
@@ -233,10 +252,12 @@ export const hyperbolic = [
 // 📖 1M free tokens — API keys at https://console.scaleway.com/iam/api-keys
 export const scaleway = [
   ['devstral-2-123b-instruct-2512',            'Devstral 2 123B',     'S+', '72.2%', '256k'],
-  ['qwen3.5-397b-a17b',                      'Qwen3.5 400B VLM',   'S',  '68.0%', '250k'],
+  ['qwen3.5-397b-a17b',                       'Qwen3.5 400B VLM',   'S',  '68.0%', '250k'],
   ['mistral/mistral-large-3-675b-instruct-2512', 'Mistral Large 675B',  'A+', '58.0%', '250k'],
   ['qwen3-235b-a22b-instruct-2507',            'Qwen3 235B',         'S+', '70.0%', '128k'],
+  ['gpt-oss-120b',                             'GPT OSS 120B',       'S',  '60.0%', '131k'],
   ['qwen3-coder-30b-a3b-instruct',             'Qwen3 Coder 30B',    'A+', '55.0%', '32k'],
+  ['holo2-30b-a3b',                           'Holo2 30B',           'A+', '52.0%', '131k'],
   ['llama-3.3-70b-instruct',                   'Llama 3.3 70B',      'A-', '39.5%', '128k'],
   ['deepseek-r1-distill-llama-70b',            'R1 Distill 70B',     'A',  '43.9%', '128k'],
   ['mistral-small-3.2-24b-instruct-2506',      'Mistral Small 3.2',  'B+', '30.0%', '128k'],
@@ -245,8 +266,11 @@ export const scaleway = [
 // 📖 Google AI Studio source - https://aistudio.google.com
 // 📖 Free Gemma models — 14.4K req/day, API keys at https://aistudio.google.com/apikey
 export const googleai = [
+  ['gemma-4-31b-it',                            'Gemma 4 31B',        'B+', '45.0%', '256k'],
+  ['gemma-4-26b-a4b-it',                        'Gemma 4 26B MoE',    'B+', '42.0%', '256k'],
   ['gemma-3-27b-it',                           'Gemma 3 27B',        'B',  '22.0%', '128k'],
   ['gemma-3-12b-it',                           'Gemma 3 12B',        'C',  '15.0%', '128k'],
+  ['gemma-4-e4b-it',                            'Gemma 4 E4B',        'C',  '12.0%', '128k'],
   ['gemma-3-4b-it',                            'Gemma 3 4B',         'C',  '10.0%', '128k'],
 ]
@@ -280,15 +304,29 @@ export const siliconflow = [
 // 📖 OpenAI-compatible endpoint: https://api.together.xyz/v1/chat/completions
 // 📖 Credits/promotions vary by account and region; verify current quota in console.
 export const together = [
+  // ── S+ tier ──
   ['moonshotai/Kimi-K2.5',                     'Kimi K2.5',          'S+', '76.8%', '128k'],
-  ['Qwen/Qwen3.5-397B-A17B',                    'Qwen3.5 400B VLM',   'S',  '68.0%', '250k'],
-  ['MiniMaxAI/MiniMax-M2.5',                    'MiniMax M2.5',       'S+', '80.2%', '200k'],
+  ['MiniMaxAI/MiniMax-M2.5',                    'MiniMax M2.5',       'S+', '80.2%', '228k'],
   ['zai-org/GLM-5',                             'GLM-5',              'S+', '77.8%', '128k'],
   ['Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8',  'Qwen3 Coder 480B',   'S+', '70.6%', '256k'],
-  ['deepseek-ai/DeepSeek-V3.1',                'DeepSeek V3.1',      'S',  '62.0%', '128k'],
-  ['deepseek-ai/DeepSeek-R1',                  'DeepSeek R1',        'S',  '61.0%', '128k'],
-  ['openai/gpt-oss-120b',                      'GPT OSS 120B',       'S',  '60.0%', '128k'],
-  ['openai/gpt-oss-20b',                       'GPT OSS 20B',        'A',  '42.0%', '128k'],
+  ['deepseek-ai/DeepSeek-V3.2',                'DeepSeek V3.2',      'S+', '73.1%', '164k'],
+  ['MiniMaxAI/MiniMax-M2.1',                    'MiniMax M2.1',       'S+', '74.0%', '197k'],
+  // ── S tier ──
+  ['Qwen/Qwen3.5-397B-A17B',                    'Qwen3.5 400B VLM',   'S',  '68.0%', '250k'],
+  ['deepseek-ai/DeepSeek-V3.1',                'DeepSeek V3.1',      'S',  '62.0%', '164k'],
+  ['deepseek-ai/DeepSeek-V3.1-Terminus',       'DeepSeek V3.1 Term', 'S',  '68.4%', '164k'],
+  ['deepseek-ai/DeepSeek-R1',                  'DeepSeek R1',        'S',  '61.0%', '164k'],
+  ['openai/gpt-oss-120b',                      'GPT OSS 120B',       'S',  '60.0%', '131k'],
+  ['Qwen/Qwen3-235B-A22B-Instruct-2507',       'Qwen3 235B 2507',    'S+', '70.0%', '131k'],
+  ['MiniMaxAI/MiniMax-M2',                      'MiniMax M2',         'S',  '69.4%', '197k'],
+  // ── A+ tier ──
+  ['nvidia/Nemotron-3-Super-120B-A12B',         'Nemotron 3 Super',   'A+', '56.0%', '128k'],
+  ['nvidia/Nemotron-3-Nano-30B-A3B',            'Nemotron Nano 30B',  'A',  '43.0%', '262k'],
+  ['Qwen/Qwen3-Coder-30B-A3B-Instruct',        'Qwen3 Coder 30B',    'A+', '55.0%', '160k'],
+  // ── A tier ──
+  ['meta-llama/Llama-4-Scout-17B-16E-Instruct', 'Llama 4 Scout',      'A',  '44.0%', '328k'],
+  ['openai/gpt-oss-20b',                       'GPT OSS 20B',        'A',  '42.0%', '131k'],
+  // ── A- tier ──
   ['meta-llama/Llama-3.3-70B-Instruct-Turbo',  'Llama 3.3 70B',      'A-', '39.5%', '128k'],
 ]
@@ -297,17 +335,27 @@ export const together = [
 // 📖 https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1/chat/completions
 // 📖 Free plan includes daily neuron quota and provider-level request limits.
 export const cloudflare = [
+  // ── S+ tier ──
   ['@cf/moonshotai/kimi-k2.5',                'Kimi K2.5',         'S+', '76.8%', '256k'],
-  ['@cf/zhipu/glm-4.7-flash',               'GLM-4.7-Flash',     'S',  '59.2%', '131k'],
-  ['@cf/openai/gpt-oss-120b',                  'GPT OSS 120B',       'S',  '60.0%', '128k'],
-  ['@cf/meta/llama-4-scout-17b-16e-instruct',  'Llama 4 Scout',    'A',  '44.0%', '131k'],
-  ['@cf/nvidia/nemotron-3-120b-a12b',           'Nemotron 3 Super', 'A+', '56.0%', '128k'],
-  ['@cf/qwen/qwen3-30b-a3b-fp8',               'Qwen3 30B MoE',    'A',  '45.0%', '128k'],
-  ['@cf/qwen/qwen2.5-coder-32b-instruct',      'Qwen2.5 Coder 32B',  'A',  '46.0%', '32k'],
-  ['@cf/deepseek-ai/deepseek-r1-distill-qwen-32b', 'R1 Distill 32B', 'A',  '43.9%', '128k'],
-  ['@cf/openai/gpt-oss-20b',                   'GPT OSS 20B',        'A',  '42.0%', '128k'],
-  ['@cf/meta/llama-3.3-70b-instruct-fp8-fast', 'Llama 3.3 70B',      'A-', '39.5%', '128k'],
-  ['@cf/meta/llama-3.1-8b-instruct',           'Llama 3.1 8B',       'B',  '28.8%', '128k'],
+  // ── S tier ──
+  ['@cf/zhipu/glm-4.7-flash',                 'GLM-4.7-Flash',     'S',  '59.2%', '131k'],
+  ['@cf/openai/gpt-oss-120b',                 'GPT OSS 120B',      'S',  '60.0%', '128k'],
+  // ── A+ tier ──
+  ['@cf/qwen/qwq-32b',                        'QwQ 32B',           'A+', '50.0%', '131k'],
+  // ── A tier ──
+  ['@cf/meta/llama-4-scout-17b-16e-instruct', 'Llama 4 Scout',     'A',  '44.0%', '131k'],
+  ['@cf/nvidia/nemotron-3-120b-a12b',          'Nemotron 3 Super',  'A+', '56.0%', '128k'],
+  ['@cf/qwen/qwen3-30b-a3b-fp8',              'Qwen3 30B MoE',     'A',  '45.0%', '128k'],
+  ['@cf/qwen/qwen2.5-coder-32b-instruct',     'Qwen2.5 Coder 32B', 'A',  '46.0%', '32k'],
+  ['@cf/deepseek-ai/deepseek-r1-distill-qwen-32b', 'R1 Distill 32B', 'A', '43.9%', '128k'],
+  // ── A- tier ──
+  ['@cf/openai/gpt-oss-20b',                  'GPT OSS 20B',       'A',  '42.0%', '128k'],
+  ['@cf/meta/llama-3.3-70b-instruct-fp8-fast','Llama 3.3 70B',     'A-', '39.5%', '128k'],
+  ['@cf/google/gemma-4-26b-a4b-it',           'Gemma 4 26B MoE',   'A-', '38.0%', '256k'],
+  ['@cf/mistralai/mistral-small-3.1-24b-instruct', 'Mistral Small 3.1', 'B+', '30.0%', '128k'],
+  // ── B tier ──
+  ['@cf/ibm/granite-4.0-h-micro',             'Granite 4.0 Micro', 'B+', '30.0%', '128k'],
+  ['@cf/meta/llama-3.1-8b-instruct',          'Llama 3.1 8B',      'B',  '28.8%', '128k'],
 ]
 // 📖 Perplexity source - https://docs.perplexity.ai
@@ -328,16 +376,20 @@ export const perplexity = [
 // 📖 Qwen3-Coder models: optimized coding models with excellent SWE-bench scores
 export const qwen = [
   // ── S+ tier — SWE-bench Verified ≥70% ──
-  ['qwen3-coder-plus',                        'Qwen3 Coder Plus',    'S+', '69.6%', '256k'],
-  ['qwen3-coder-480b-a35b-instruct',          'Qwen3 Coder 480B',    'S+', '70.6%', '256k'],
+  ['qwen3.6-plus',                              'Qwen3.6 Plus',      'S+', '78.8%', '1M'],
+  ['qwen3-coder-plus',                        'Qwen3 Coder Plus',  'S+', '69.6%', '256k'],
+  ['qwen3-coder-480b-a35b-instruct',          'Qwen3 Coder 480B',   'S+', '70.6%', '256k'],
   // ── S tier — SWE-bench Verified 60–70% ──
-  ['qwen3-coder-max',                         'Qwen3 Coder Max',     'S',  '67.0%', '256k'],
-  ['qwen3-coder-next',                        'Qwen3 Coder Next',    'S',  '65.0%', '256k'],
-  ['qwen3-235b-a22b-instruct',                'Qwen3 235B',          'S',  '70.0%', '256k'],
-  ['qwen3-next-80b-a3b-instruct',             'Qwen3 80B Instruct',  'S',  '65.0%', '128k'],
+  ['qwen3.5-plus',                             'Qwen3.5 Plus',      'S',  '68.0%', '1M'],
+  ['qwen3-coder-max',                         'Qwen3 Coder Max',   'S',  '67.0%', '256k'],
+  ['qwen3-coder-next',                        'Qwen3 Coder Next',  'S',  '65.0%', '256k'],
+  ['qwen3-235b-a22b-instruct',                'Qwen3 235B',         'S',  '70.0%', '256k'],
+  ['qwen3-next-80b-a3b-instruct',             'Qwen3 80B Instruct', 'S',  '65.0%', '128k'],
   // ── A+ tier — SWE-bench Verified 50–60% ──
-  ['qwen3-32b',                               'Qwen3 32B',           'A+', '50.0%', '128k'],
-  ['qwen2.5-coder-32b-instruct',              'Qwen2.5 Coder 32B',   'A',  '46.0%', '32k'],
+  ['qwen3-32b',                               'Qwen3 32B',          'A+', '50.0%', '128k'],
+  ['qwen2.5-coder-32b-instruct',              'Qwen2.5 Coder 32B',  'A',  '46.0%', '32k'],
+  // ── B+ tier ──
+  ['qwen3.5-flash',                            'Qwen3.5 Flash',     'B+', '55.0%', '1M'],
 ]
 // 📖 iFlow source - https://platform.iflow.cn
@@ -361,6 +413,15 @@ export const iflow = [
   ['qwen3-max',                               'Qwen3 Max',           'A+', '55.0%', '256k'],
 ]
+// 📖 Chutes AI - Decentralized serverless AI compute (Bittensor Subnet 64)
+// 📖 Truly free (community GPU-powered), no credit card required
+export const chutes = [
+  ['deepseek-ai/DeepSeek-R1',                  'DeepSeek R1',          'S',  '61.0%', '64k'],
+  ['meta-llama/Llama-3.1-70B-Instruct',        'Llama 3.1 70B',        'A-', '39.5%', '128k'],
+  ['Qwen/Qwen2.5-72B-Instruct',                'Qwen 2.5 72B',         'A',  '42.0%', '32k'],
+  ['Qwen/Qwen2.5-Coder-32B-Instruct',          'Qwen2.5 Coder 32B',    'A',  '46.0%', '32k'],
+]
 // 📖 Rovo Dev CLI source - https://www.atlassian.com/rovo
 // 📖 CLI tool only - no API endpoint - requires 'acli rovodev run'
 // 📖 Install: https://support.atlassian.com/rovo/docs/install-and-run-rovo-dev-cli-on-your-device/
@@ -369,16 +430,20 @@ export const iflow = [
 export const rovo = [
   ['anthropic/claude-sonnet-4.6',       'Claude Sonnet 4.6',    'S+', '75.0%', '200k'],
   ['anthropic/claude-opus-4.6',         'Claude Opus 4.6',      'S+', '80.0%', '200k'],
+  ['openai/gpt-5.2',                    'GPT-5.2',              'S+', '72.0%', '400k'],
+  ['openai/gpt-5.2-codex',              'GPT-5.2 Codex',        'S+', '74.0%', '400k'],
+  ['anthropic/claude-haiku-4.5',        'Claude Haiku 4.5',     'A+', '50.0%', '200k'],
 ]
 // 📖 Gemini CLI source - https://github.com/google-gemini/gemini-cli
 // 📖 CLI tool with OpenAI-compatible API support
 // 📖 Install: npm install -g @google/gemini-cli
 // 📖 Free tier: 1,000 req/day with personal Google account (no credit card)
-// 📖 Models: Gemini 3 Pro (76.2% SWE-bench), Gemini 2.5 Pro, Gemini 2.5 Flash
+// 📖 Models: Gemini 3.1 Pro, Gemini 2.5 Pro, Gemini 2.5 Flash
+// 📖 Note: Gemini 3 Pro was shut down March 9, 2026 — replaced by Gemini 3.1 Pro
 // 📖 Supports custom OpenAI-compatible providers via GEMINI_API_BASE_URL
 export const gemini = [
-  ['google/gemini-3-pro',               'Gemini 3 Pro 🆕',      'S+', '76.2%', '1M'],
+  ['google/gemini-3.1-pro',             'Gemini 3.1 Pro',      'S+', '78.0%', '1M'],
   ['google/gemini-2.5-pro',             'Gemini 2.5 Pro',      'S+', '63.2%', '1M'],
   ['google/gemini-2.5-flash',           'Gemini 2.5 Flash',    'A+', '50.0%', '1M'],
 ]
@@ -389,11 +454,13 @@ export const gemini = [
 // 📖 Login: https://opencode.ai/auth — get your Zen API key
 // 📖 Config: set provider to opencode/<model-id> in OpenCode config
 export const opencodeZen = [
-  ['big-pickle',                              'Big Pickle 🆕',             'S+', '72.0%', '200k'],
-  ['gpt-5-nano',                              'GPT 5 Nano 🆕',            'S',  '65.0%', '128k'],
-  ['mimo-v2-flash-free',                      'MiMo V2 Flash Free 🆕',    'S+', '73.4%', '256k'],
-  ['minimax-m2.5-free',                       'MiniMax M2.5 Free 🆕',     'S+', '80.2%', '200k'],
-  ['nemotron-3-super-free',                   'Nemotron 3 Super Free 🆕',  'A+', '52.0%', '128k'],
+  ['big-pickle',                              'Big Pickle',           'S+', '72.0%', '200k'],
+  ['mimo-v2-pro-free',                       'MiMo V2 Pro Free',    'S+', '75.0%', '1M'],
+  ['mimo-v2-flash-free',                      'MiMo V2 Flash Free',  'S+', '73.4%', '262k'],
+  ['mimo-v2-omni-free',                       'MiMo V2 Omni Free',  'S+', '73.0%', '262k'],
+  ['gpt-5-nano',                              'GPT 5 Nano',          'S',  '65.0%', '400k'],
+  ['minimax-m2.5-free',                       'MiniMax M2.5 Free',   'S+', '80.2%', '200k'],
+  ['nemotron-3-super-free',                   'Nemotron 3 Super Free','A+', '52.0%', '1M'],
 ]
 // 📖 All sources combined - used by the main script
@@ -518,19 +585,24 @@ export const sources = {
     binary: 'gemini',
     checkArgs: ['--version'],
   },
-  // 📖 OpenCode Zen free models — hosted AI gateway, only runs on OpenCode CLI / Desktop
   'opencode-zen': {
     name: 'OpenCode Zen',
     url: 'https://opencode.ai/zen/v1/chat/completions',
     models: opencodeZen,
     zenOnly: true,
   },
+  chutes: {
+    name: 'Chutes AI',
+    url: 'https://chutes.ai/v1/chat/completions',
+    models: chutes,
+  },
 }
 // 📖 Flatten all models from all sources — each entry includes providerKey as 6th element
 // 📖 providerKey lets the main CLI know which API key and URL to use per model
-export const MODELS = []
+export const MODELS = [];
 for (const [sourceKey, sourceData] of Object.entries(sources)) {
+  if (!sourceData || !sourceData.models) continue
   for (const [modelId, label, tier, sweScore, ctx] of sourceData.models) {
     MODELS.push([modelId, label, tier, sweScore, ctx, sourceKey])
   }

package/src/provider-metadata.js CHANGED Viewed

@@ -59,6 +59,7 @@ export const ENV_VAR_NAMES = {
   perplexity: 'PERPLEXITY_API_KEY',
   zai:        'ZAI_API_KEY',
   gemini:     'GEMINI_API_KEY',
+  chutes:     'CHUTES_API_KEY',
 }
 // 📖 OPENCODE_MODEL_MAP: sparse table of model IDs that differ between sources.js and OpenCode's
@@ -66,7 +67,6 @@ export const ENV_VAR_NAMES = {
 export const OPENCODE_MODEL_MAP = {
   groq: {
     'moonshotai/kimi-k2-instruct': 'moonshotai/kimi-k2-instruct-0905',
-    'meta-llama/llama-4-scout-17b-16e-preview': 'meta-llama/llama-4-scout-17b-16e-instruct',
     'meta-llama/llama-4-maverick-17b-128e-preview': 'meta-llama/llama-4-maverick-17b-128e-instruct',
   }
 }
@@ -250,4 +250,11 @@ export const PROVIDER_METADATA = {
     rateLimits: 'Free tier models — requires OpenCode Zen API key',
     zenOnly: true,
   },
+  chutes: {
+    label: 'Chutes AI',
+    color: chalk.rgb(144, 238, 144),
+    signupUrl: 'https://chutes.ai',
+    signupHint: 'Sign up and generate an API key',
+    rateLimits: 'Free (community GPU-powered), no hard cap',
+  },
 }